speech to speech
A voice pipeline in which one model listens and answers in audio directly, as opposed to chaining speech to text, a text model and text to speech.
In more detail
Speech to speech gives quicker, more natural turns; the chained design gives more control, since you can inspect, filter and log the text between steps. Speech to speech also makes it harder to filter or log what the model says before it is heard.
Related terms
- speech to text — Converting spoken audio into text, often with a timestamp for each word.
- text to speech — Generating spoken audio from text with a voice model.
Taught in
- Workflows Before Agents — AI Engineering: LLM Apps, RAG & Agents
- Images, Audio And Speech — AI Engineering: LLM Apps, RAG & Agents